In plain words: A math framework tracks how people and language models turn content into true-or-false statements about possible worlds. It argues models never connect words to real things—the symbol grounding problem—but bypass that need entirely.
Abstract · A Categorical Analysis of Large Language Models and Why LLMs Circumvent the Symbol Grounding Problem
This paper presents a formal, categorical framework for analysing how humans and large language models (LLMs) transform content into truth-evaluated propositions about a state space of possible worlds W , in order to argue that LLMs do not solve but circumvent the symbol grounding problem.
Luciano Floridi, Yiyang Jia, Fernando Tohmé
arXiv:2512.09117 · cs.AI · submitted Dec 9, 2025
abstract · pdf · html